Agentic Examples for SAP Generative AI Hub

The examples below showcase how to use different agentic frameworks with the SAP provider via LiteLMM. Users can access LLMs across all vendors (OpenAI, Google, Amazon, Mistral, SAP, ...) available in the Generative AI Hub. Each framework example is described in a separate jupyter notebook.

Prerequisites

• AI Core Gen AI subscription via BTP tenant.
• Install latest Litellm (including SAP provider).

1. Langgraph

• langgraph_agent notebook

2. CrewAI

• crewai_litellm_lib notebook
• crewai_litellm_proxy notebook

3. PydanticAI

• pydanticai_litellm notebook

4. Google ADK

• google_adk notebook

5. OpenAI ADK

• openai_adk.py

6. AWS

• aws_strands notebook

7. LlamaIndex

• Llamaindex_litellm notebook

8. smolagents

• smolagents_litellm notebook

9. MSFT Agent Framework

• msft_agent_litellm notebook

10. Agentscope

• agentscope_litellm notebook

11. AG2

• ag2_litellm notebook

Note for Maintainers of these examples

Clear cell outputs and metadata using the ".pre-commit-config.yaml". Installation procedure:

python3 -m venv env
source env/bin/activate
python3 -m pip install pre-commit nbstripout

Manual run:

pre-commit run --all-files

Skip Hooks temporarily:

git commit -m "Message" --no-verify